Lucian Ghinda
lucianghinda.com
Lucian Ghinda
@lucianghinda.com
Product Engineer, Ruby on Rails Developer

‣ Curator of newsletter.shortruby.com
‣ Helping #Ruby developers design better test cases at https://goodenoughtesting.com
Phew, what a relief!

Codex 5.3 confirmed: I wasn't crazy for thinking, based on my manual testing, that there was a bug 😄
February 7, 2026 at 12:26 PM
3️⃣ agents_skill_vault

A gem that can manage a vault (a local folder) with various skills from Github URLs

Basically you can give it a list of Agent Skills (or repositories) and it will download and sync them on a local folder.

github.com/lucianghind...
February 4, 2026 at 11:30 AM
2️⃣ agent_skill_parser
A Ruby gem for parsing skill files that use YAML frontmatter and markdown body content.

It will parse an AgentSkill file according with specifications from agentskills dot io and return an object with those properties

github.com/lucianghind...
February 4, 2026 at 11:30 AM
1️⃣ agent_skills_configurations

A unified interface for discovering and accessing skill configuration paths for various AI coding agents.
It will give you the configuration location/folder per each installed (or not) AI coding agent.

github.com/lucianghind...
February 4, 2026 at 11:30 AM
For engineering leaders: the study's conclusion matters for your teams.
If your developers rely heavily on AI for code generation, you need processes that ensure they understand what's being generated.
During incidents or debugging sessions under pressure, they need those skills
February 2, 2026 at 8:30 AM
Another key insight: encountering errors and debugging them plays a crucial role in skill formation.

The control group (no AI) hit errors, had to understand why they happened, and learned through fixing them. This can't be fast-tracked.
February 2, 2026 at 8:30 AM
2. Ask AI to generate code AND provide explanations in the same response

These participants spent more time reading but developed better understanding. The explanation forced them to engage with the concepts, not just copy the solution.
February 2, 2026 at 8:30 AM
But here's the practical part. The study found two approaches that worked well for both completion and comprehension:

1. Generate code with AI, then ask follow-up questions to understand what it did

This group showed strong understanding in their quiz results.
February 2, 2026 at 8:30 AM
The core finding: developers who completed tasks without AI assistance scored higher on comprehension tests.

Using AI to generate code doesn't automatically translate to understanding that code. This held true across all experience levels.
February 2, 2026 at 8:30 AM
One interesting finding from their pilot: even when explicitly told not to use AI, 25-35% of participants still did.

This shows how deeply integrated AI has become in some workflows. We reach for it almost instinctively now.
February 2, 2026 at 8:30 AM
ChatGPT agrees with me:
February 2, 2026 at 8:30 AM
For me looking at this table seems like most of them were senior developers. Maybe it is typo/bug in the article they published.
February 2, 2026 at 8:30 AM
Quick note on methodology: the article calls them mostly junior engineers, but the data shows 55.8% have 7+ years of coding experience and 36.5% have 4-6 years.

This matters because the findings apply more to experienced developers learning new concepts than absolute beginners.
February 2, 2026 at 8:30 AM
Here is OpenCode with GLM deciding to skip some tests because it couldn't make them pass. :)

Let's talk about using generative AI to write test cases this Thursday, in person, at the Sibiu Web Meetup in Sibiu.
January 27, 2026 at 1:06 PM
Working on my presentation about AI-assisted, human-approved testing that I will deliver this Thursday at Sibiu Web Meetup

If you are in Sibiu join here -> luma.com/ps4gax1s
January 26, 2026 at 4:53 PM
If you're writing API documentation, always specify units for duration parameters.

Not just "timeout: 30" but "timeout: 30 seconds" or better yet name the parameter if you can "timeout_in_seconds"
January 22, 2026 at 8:30 AM
After configuring lazygit with delta it looks like this:
January 16, 2026 at 10:36 AM
And here is the difference, before it was looking like this:
January 16, 2026 at 10:36 AM
I use lazygit for managing git workflow and configuring it to work with delta is as simple as adding a line there:
January 16, 2026 at 10:36 AM
This is how git diff looks before and after using delta
January 16, 2026 at 10:36 AM
Install delta github.com/dandavison/... then configure .gitconfig:
January 16, 2026 at 10:36 AM
Seems like Ruby is pretty well positioned as a language that is token-efficient when used with LLMs.

Source "Which programming languages are most token-efficient?" by Martin Alderson martinalderson.com/posts/which...
January 13, 2026 at 8:30 AM
If you are doing some planning this week, consider adding checkpoints for upgrading your #Rails app

Specifically, if you are still running Rails 7.2T.x
Security fixes end: August 9, 2026

Maybe it sounds like there is enough time but time flies.
January 5, 2026 at 11:40 AM
This edition is packed with goodies released/announced/launched for #Ruby community.

Make sure you set aside some time these weeks to go through it -> newsletter.shortruby.com/p/edition-162
December 23, 2025 at 2:34 PM
Ruby's new identity statement caught my attention:

"A language where people gather, a site where people are visible."

Source: www.ruby-lang.org/en/news/202...
December 23, 2025 at 9:20 AM